According to an aspect of some embodiments of the present invention there is provided a system for imaging of objects in a scene. The system contains a hardware processor, or multiple hardware processors, which execute(s) code for: receiving, from a first sensor, image or images depicting an object or objects, where the object(s) include(s) an autonomous navigation system that controls a course of the object(s) in space, predicting a spatiotemporal profile of the object(s) within the image(s), and generating instructions for execution by a second sensor for capturing an image of the object(s) at a time and location corresponding to the spatiotemporal profile.
Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
2. The system of claim 1, wherein each respective spatiotemporal profile is associated with a probability value indicative of likelihood of the respective object being present at the future time and spatial location, wherein the scheduling is optimized according to the probability values of the plurality of spatiotemporal profiles.
A system for optimizing scheduling based on spatiotemporal profiles of objects involves predicting future positions and times of objects within a defined space. The system generates multiple spatiotemporal profiles for each object, where each profile represents a potential future position and time. Each profile is assigned a probability value indicating the likelihood that the object will actually be present at the predicted location and time. The system then uses these probability values to optimize scheduling decisions, ensuring that tasks or resources are allocated in a way that maximizes efficiency based on the predicted presence of objects. This approach is particularly useful in applications where dynamic object tracking and predictive scheduling are critical, such as logistics, autonomous navigation, or resource management. By incorporating probabilistic assessments of object locations, the system improves decision-making accuracy and reduces uncertainty in scheduling processes. The optimization process considers the likelihood of each predicted spatiotemporal event, allowing for adaptive and data-driven scheduling strategies.
3. The system of claim 1, wherein each respective spatiotemporal profile is associated with an estimated image quality of an image of the respective object when captured by said single second sensor at a corresponding future time and spatial location.
4. The system of claim 1, wherein a plurality of second sensors are located at a plurality of spaced apart spatial locations and/or at a plurality of viewing angles, and the scheduling is performed for capturing the at least one image of each object using a respective second sensor of the plurality of second sensors for meeting a set of image quality rules.
6. The system of claim 1, wherein sequentially capturing an image of said each of said maximum number of different objects is by imaging by the single second sensor different objects at different spatial locations and/or different times by sweeping the single second sensor from a first direction to a second direction, first objects appearing at the first direction at a first time point are scheduled followed by objects appearing in the second direction at a second time point later than said first time point.
7. The system of claim 1, wherein said different objects are persons and wherein said hardware processor further executing code for analyzing using biometric analysis said at least one image of each of said maximum number of different persons captured by said single second sensor to identify said different persons.
The invention relates to a surveillance system that uses multiple sensors to capture images of multiple persons in a monitored area. The system addresses the challenge of accurately identifying individuals in crowded or dynamic environments where traditional surveillance methods may fail due to occlusions, low resolution, or limited coverage. The system includes a primary sensor for capturing images of a monitored area and at least one secondary sensor for capturing additional images of specific regions within the area. The secondary sensor is activated based on detected motion or other triggers, ensuring focused and high-resolution imaging of individuals. The system processes these images to identify and track multiple persons simultaneously, improving surveillance accuracy and efficiency. The hardware processor executes code to analyze the captured images using biometric analysis, such as facial recognition or gait analysis, to identify the different persons. This biometric analysis enhances the system's ability to distinguish between individuals, even in challenging conditions. The system is designed to operate in real-time, providing continuous monitoring and identification of persons within the monitored area. The integration of multiple sensors and advanced biometric analysis ensures robust and reliable surveillance capabilities.
8. The system of claim 1, wherein said different objects are vehicles and wherein said hardware processor further executing code for analyzing said at least one image of each of said maximum number of different vehicles captured by said single second sensor to identify license plates of said different vehicles.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
November 6, 2019
October 25, 2022
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.